suppressPackageStartupMessages(library(tidyverse))
library(targets)
library(tarchetypes)
library(DT)knitr::opts_knit$set(root.dir = "../../")df_mm <- tar_read(df_mm)
df_mm %>%
select(category_id, activity_id_new, has_finding, everything())## # A tibble: 4,055 × 185
## category_id activity_id_new has_finding start_date n_visit n_unsch_visit n_sched_visit ratio_unsch_visit ratio_unsch_visit_rnk n_ae n_sae ae_per_visit sae_per_visit ae_per_visit_rnk
## <chr> <chr> <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 cnsn 00001 yes 2015-01-01 732 26 706 0.0355 0.289 178 4 0.243 0.00546 0.206
## 2 cnsn 00003 yes 2014-01-01 NA NA NA NA NA NA NA NA NA NA
## 3 cnsn 00004 yes 2015-01-01 181 33 148 0.182 0.761 108 8 0.597 0.0442 0.701
## 4 cnsn 00006 yes 2014-01-01 0 0 0 NaN 0.990 6 0 NA NA 0
## 5 cnsn 00008 yes 2015-01-01 114 0 114 0 0.273 3 0 0.0263 0 0.481
## 6 cnsn 00009 yes 2015-01-01 297 0 297 0 0 23 5 0.0774 0.0168 0.243
## 7 cnsn 00012 yes 2015-01-01 446 7 439 0.0157 0.333 147 17 0.330 0.0381 0.410
## 8 cnsn 00013 yes 2015-01-01 688 65 623 0.0945 0.594 172 27 0.25 0.0392 0.203
## 9 cnsn 00015 yes 2015-01-01 141 17 124 0.121 0.717 69 3 0.489 0.0213 0.767
## 10 cnsn 00016 yes 2015-01-01 0 0 0 NaN 0.433 32 5 NA NA 0.433
## # … with 4,045 more rows, and 171 more variables: sae_per_visit_rnk <dbl>, median_ae_reporting_delay <dbl>, mean_ae_reporting_delay <dbl>, max_ae_reporting_delay <dbl>,
## # median_sae_reporting_delay <dbl>, mean_sae_reporting_delay <dbl>, max_sae_reporting_delay <dbl>, n_patients <dbl>, therapeutic_area <chr>, n_active_sites_pi_yy <dbl>,
## # n_active_sites_pi_yy_rnk <dbl>, n_active_trials_at_site_in_ta_yy <dbl>, n_active_trials_at_site_in_ta_yy_rnk <dbl>, time_on_study_dd <dbl>, dev_data_available <chr>,
## # n_maj_dev <dbl>, n_min_dev <dbl>, n_maj_dev_per_daysonstudy <dbl>, n_min_dev_per_daysonstudy <dbl>, n_maj_dev_per_daysonstudy_rnk <dbl>, n_min_dev_per_daysonstudy_rnk <dbl>,
## # issue_data_available <chr>, mean_iss_completion_time <dbl>, median_iss_completion_time <dbl>, max_iss_completion_time <dbl>, n_iss_open <dbl>, n_iss_open_per_pat <dbl>,
## # n_iss_due <dbl>, n_iss_compl <dbl>, n_iss_compl_per_daysonstudy <dbl>, n_iss_late <dbl>, n_iss_cnsn_open <dbl>, n_iss_cnsn_due <dbl>, n_iss_cnsn_compl <dbl>,
## # n_iss_cnsn_late <dbl>, n_iss_dtin_open <dbl>, n_iss_dtin_due <dbl>, n_iss_dtin_compl <dbl>, n_iss_dtin_late <dbl>, n_iss_ptpe_open <dbl>, n_iss_ptpe_due <dbl>, …tibble(columns = colnames(df_mm)) %>%
DT::datatable()df_mm_bin <- tar_read(df_mm_bin)
df_mm_bin %>%
select(category_id, activity_id_new, has_finding, everything())## # A tibble: 4,055 × 861
## category_id activity_id_new has_finding nvisitLL nvisitML nvisitM nvisitMH nvisitHH nvisitNA nunschvisitLL nunschvisitML nunschvisitM nunschvisitMH nunschvisitHH nunschvisitNA
## <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 cnsn 00001 yes 0 0 0 1 0 0 0 0 0 1 0 0
## 2 cnsn 00003 yes 0 0 0 0 0 1 0 0 0 0 0 1
## 3 cnsn 00004 yes 0 0 1 0 0 0 0 0 0 1 0 0
## 4 cnsn 00006 yes 1 0 0 0 0 0 1 0 0 0 0 0
## 5 cnsn 00008 yes 0 1 0 0 0 0 1 0 0 0 0 0
## 6 cnsn 00009 yes 0 0 1 0 0 0 1 0 0 0 0 0
## 7 cnsn 00012 yes 0 0 0 1 0 0 0 1 0 0 0 0
## 8 cnsn 00013 yes 0 0 0 1 0 0 0 0 0 0 1 0
## 9 cnsn 00015 yes 0 1 0 0 0 0 0 0 1 0 0 0
## 10 cnsn 00016 yes 1 0 0 0 0 0 1 0 0 0 0 0
## # … with 4,045 more rows, and 846 more variables: nschedvisitLL <dbl>, nschedvisitML <dbl>, nschedvisitM <dbl>, nschedvisitMH <dbl>, nschedvisitHH <dbl>, nschedvisitNA <dbl>,
## # ratiounschvisitLL <dbl>, ratiounschvisitML <dbl>, ratiounschvisitM <dbl>, ratiounschvisitMH <dbl>, ratiounschvisitHH <dbl>, ratiounschvisitNA <dbl>, ratiounschvisitrnkLL <dbl>,
## # ratiounschvisitrnkML <dbl>, ratiounschvisitrnkM <dbl>, ratiounschvisitrnkMH <dbl>, ratiounschvisitrnkHH <dbl>, ratiounschvisitrnkNA <dbl>, naeLL <dbl>, naeML <dbl>, naeM <dbl>,
## # naeMH <dbl>, naeHH <dbl>, naeNA <dbl>, nsaeLL <dbl>, nsaeML <dbl>, nsaeM <dbl>, nsaeMH <dbl>, nsaeHH <dbl>, nsaeNA <dbl>, aepervisitLL <dbl>, aepervisitML <dbl>,
## # aepervisitM <dbl>, aepervisitMH <dbl>, aepervisitHH <dbl>, aepervisitNA <dbl>, saepervisitLL <dbl>, saepervisitML <dbl>, saepervisitM <dbl>, saepervisitMH <dbl>,
## # saepervisitHH <dbl>, saepervisitNA <dbl>, aepervisitrnkLL <dbl>, aepervisitrnkML <dbl>, aepervisitrnkM <dbl>, aepervisitrnkMH <dbl>, aepervisitrnkHH <dbl>, aepervisitrnkNA <dbl>,
## # saepervisitrnkLL <dbl>, saepervisitrnkML <dbl>, saepervisitrnkM <dbl>, saepervisitrnkMH <dbl>, saepervisitrnkHH <dbl>, saepervisitrnkNA <dbl>, medianaereportingdelayLL <dbl>, …tibble(columns = colnames(df_mm_bin)) %>%
DT::datatable()Modelling coefficients have been preselected.
tar_read(df_form) %>%
DT::datatable()Indeces of modelling matrix that defines time series cross validation strategy.
tar_read(df_cv)## # A tibble: 45 × 4
## year_start_act category_id index_past index_next_year
## <dbl> <chr> <chr> <chr>
## 1 2011 cnsn 70,71,72,84,85,86,87,88,89,90,91,92,93,94,95,96,108,109,110,111,113,114,11… 155,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,187,188,189,…
## 2 2012 cnsn 70,71,72,84,85,86,87,88,89,90,91,92,93,94,95,96,108,109,110,111,113,114,11… 211,229,231,234,241,242,243,244,245,246,247,249,257,258,259,260,261,262,263,…
## 3 2013 cnsn 70,71,72,84,85,86,87,88,89,90,91,92,93,94,95,96,108,109,110,111,113,114,11… 2,4,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,…
## 4 2014 cnsn 2,4,70,71,72,84,85,86,87,88,89,90,91,92,93,94,95,96,108,109,110,111,113,11… 1,3,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,31…
## 5 2015 cnsn 1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28… 30,34,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,6…
## 6 2016 cnsn 1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28… 98,99,100,101,102,103,106,141,142,143,144,145,146,161,162,163,164,165,166,16…
## 7 2017 cnsn 1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28… 228,238,239,240,248,251,252,253,254,255,256,611,633,650,651,652,653,654,655,…
## 8 2018 cnsn 1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28… 358,359,360,361,362,363,364,365,366,367,369,370,371,698,785,786,787,788,789,…
## 9 2019 cnsn 1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28… 368,805,808
## 10 2015 dtin 5678,5679,5680,5681,5682,5683,5684,5685,5686,5687,5688,5689,5690,5691,5692… 5698,5714,5715,5724,5725,5726,5727,5728,5729,5730,5731,5732,5733,5734,5735,5…
## # … with 35 more rowsAll names of all features and their variations.
tar_read(df_feat_lookup) %>%
DT::datatable()All finding statements mapped to clinical impact factors.
tar_read(df_cat_lookup) %>%
DT::datatable()